Detection of moving objects in video using a robust motion similarity measure

We propose a shape matching algorithm for deformed shapes based on dynamic programming. Our algorithm is capable of grouping together segments at fine r scales in order to come up with appropriate correspondences with segments at coarser scales. We illustrate the effectiveness of our algorithm in ret rieval of shapes hv content on two different two-dimensional (2-D) datasets , one of static hand gesture shapes and another of marine life shapes. We a lso demonstrate the superiority of our ap approach over traditional approac hes to shape matching and retrieval, such as Fourier descriptors and geomet ric and sequential moments. Our evaluation is based on human relevance judg ments following a well-established methodology from the information retriev al field.